Transcript Text Mining

Text Mining: Tools,
Techniques, and Applications
Nathan Treloar
President
AvaQuest, Inc.
Outline





Text Mining Defined
Foundations of Text Mining
Example Applications
User Interface Challenges
The Future
© 2002, AvaQuest Inc.
Mining Medical Literature


Medical research
Find causal links between
symptoms or diseases and drugs or
chemicals.
© 2002, AvaQuest Inc.
A Real Example

Research objective:
–

Data:
–

Follow chains of causal implication to discover a
relationship between migraines and biochemical
levels.
medical research papers, medical news
(unstructured text information)
Key concept types:
–
symptoms, drugs, diseases, chemicals…
© 2002, AvaQuest Inc.
Example Application: Medical
Research








stress is associated with migraines
stress can lead to loss of magnesium
calcium channel blockers prevent some migraines
magnesium is a natural calcium channel blocker
spreading cortical depression (SCD) is implicated
in some migraines
high levels of magnesium inhibit SCD
migraine patients have high platelet aggregability
magnesium can suppress platelet aggregability
(source: Swanson and Smalheiser, 1994)
© 2002, AvaQuest Inc.
Text Mining Defined

Discover useful and previously unknown
“gems” of information in large text
collections
© 2002, AvaQuest Inc.
“Search” versus “Discover”
Structured
Data
Unstructured
Data (Text)
Search
(goal-oriented)
Discover
(opportunistic)
Data
Retrieval
Data
Mining
Information
Retrieval
Text
Mining
© 2002, AvaQuest Inc.
Data Retrieval

Find records within a structured
database.
Database Type
Structured
Search Mode
Goal-driven
Atomic entity
Data Record
Example Information Need
“Find a Japanese restaurant in Boston
that serves vegetarian food.”
Example Query
“SELECT * FROM restaurants WHERE
city = boston AND type = japanese
AND has_veg = true”
© 2002, AvaQuest Inc.
Information Retrieval

Find relevant information in an
unstructured information source
(usually text)
Database Type
Unstructured
Search Mode
Goal-driven
Atomic entity
Document
Example Information Need
“Find a Japanese restaurant in Boston
that serves vegetarian food.”
Example Query
“Japanese restaurant Boston” or
Boston->Restaurants->Japanese
© 2002, AvaQuest Inc.
Data Mining

Discover new knowledge
through analysis of data
Database Type
Structured
Search Mode
Opportunistic
Atomic entity
Numbers and Dimensions
Example Information Need
“Show trend over time in # of visits to
Japanese restaurants in Boston ”
Example Query
“SELECT SUM(visits) FROM restaurants
WHERE city = boston AND type =
japanese ORDER BY date”
© 2002, AvaQuest Inc.
Text Mining

Discover new knowledge
through analysis of text
Database Type
Unstructured
Search Mode
Opportunistic
Atomic entity
Language feature or concept
Example Information Need
“Find the types of food poisoning most
often associated with Japanese
restaurants”
Example Query
Rank diseases found associated with
“Japanese restaurants”
© 2002, AvaQuest Inc.
Motivation for Text Mining


Approximately 90% of the world’s data is held in
unstructured formats (source: Oracle Corporation)
Information intensive business processes demand
that we transcend from simple document retrieval to
“knowledge” discovery.
10%
90%
Structured Numerical or Coded
Information
Unstructured or Semi-structured
Information
© 2002, AvaQuest Inc.
Challenges of Text Mining

Very high number of possible “dimensions”
–

Unlike data mining:
–
–

records (= docs) are not structurally identical
records are not statistically independent
Complex and subtle relationships between concepts in
text
–
–

All possible word and phrase types in the language!!
“AOL merges with Time-Warner”
“Time-Warner is bought by AOL”
Ambiguity and context sensitivity
–
–
automobile = car = vehicle = Toyota
Apple (the company) or apple (the fruit)
© 2002, AvaQuest Inc.
The Emergence of Text Mining

Advances in text processing technology
–
–

Natural Language Processing (NLP)
Computational Linguistics
Cheap Hardware!
–
–
–
CPU
Disk
Network
© 2002, AvaQuest Inc.
Text Processing

Statistical Analysis
–

Quantify text data
Language or Content Analysis
–
–
–
Identifying structural elements
Extracting and codifying meaning
Reducing the dimensions of text data
© 2002, AvaQuest Inc.
Statistical Analysis

Use statistics to add a numerical
dimension to unstructured text
Term frequency
Document frequency
Term proximity
Document length
© 2002, AvaQuest Inc.
Content Analysis

Lexical and Syntactic Processing
–
–
–

Semantic Processing
–
–

Extracting meaning
Named Entity Extraction (People names, Company Names,
Locations, etc…)
Extra-semantic features
–

Recognizing “tokens” (terms)
Normalizing words
Language constructs (parts of speech, sentences, paragraphs)
Identify feelings or sentiment in text
Goal = Dimension Reduction
© 2002, AvaQuest Inc.
Syntactic Processing

Lexical analysis
–
–

Recognizing word boundaries
Relatively simple process in English
Syntactic analysis
–
–
–
–
Recognizing larger constructs
Sentence and Paragraph Recognition
Parts of speech tagging
Phrase recognition
© 2002, AvaQuest Inc.
Named Entity Extraction


Identify and type language features
Examples:






People names
Company names
Geographic location names
Dates
Monetary amount
Others… (domain specific)
© 2002, AvaQuest Inc.
Simple Entity Extraction
“The quick brown fox jumps over the lazy dog”
Noun phrase
Noun phrase
Mammal
Mammal
Canidae
Canidae
© 2002, AvaQuest Inc.
Entity Extraction in Use

Categorization
–

Summarization
–

Get the “gist” of a document or document collection
Query expansion
–

Assign structure to unstructured content to facilitate
retrieval
Expand query terms with related “typed” concepts
Text Mining
–
Find patterns, trends, relationships between
concepts in text
© 2002, AvaQuest Inc.
Extra-semantic Information

Extracting hidden meaning or sentiment based
on use of language.
–
Examples:



Sentiment is:
–
–
–

“Customer is unhappy with their service!”
Sentiment = discontent
Emotions: fear, love, hate, sorrow
Feelings: warmth, excitement
Mood, disposition, temperament, …
Or even (someday)…
–
Lies, sarcasm
© 2002, AvaQuest Inc.
Text Mining:
General Applications

Relationship Analysis
–

Trend analysis
–

If A is related to B, and B is related to C, there is
potentially a relationship between A and C.
Occurrences of A peak in October.
Mixed applications
–
Co-occurrence of A together with B peak in
November.
© 2002, AvaQuest Inc.
Text Mining:
Business Applications

Ex 1: Decision Support in CRM
-

Ex 2: Knowledge Management
–

What are customers’ typical complaints?
What is the trend in the number of satisfied
customers in Cleveland?
People Finder
Ex 3: Personalization in eCommerce
-
Suggest products that fit a user’s interest profile
(even based on personality info).
© 2002, AvaQuest Inc.
Example 1:
Decision Support using Bank Call
Center Data

The Needs:
–
–
Analysis of call records as input into
decision-making process of Bank’s
management
Quick answers to important questions



–
Which offices receive the most angry calls?
What products have the fewest satisfied customers?
(“Angry” and “Satisfied” are recognizable sentiments)
User friendly interface and visualization
tools
© 2002, AvaQuest Inc.
Example 1:
Decision Support using Bank Call
Center Data

The Information Source:
–
–
Call center records
Example:
AC2G31, 01, 0101, PCC, 021, 0053352,
NEW YORK, NY, H-SUPRVR8, STMT,
“mr stark has been with the company for
about 20 yrs. He hates his stmt format and
wishes that we would show a daily balance
to help him know when he falls below the
required balance on the account.”
© 2002, AvaQuest Inc.
Example 1:
Call Volume by Sentiment
Negative Calls Related to Bank
Statements
1000
800
600
Cleveland
New York
Boston
400
200
0
© 2002, AvaQuest Inc.
Example 2:
KM People Finder

The Needs:
-
-
-
-
Find people as well as documents that
can address my information need.
Promote collaboration and knowledge
sharing
Leverage existing information access
system
The Information Sources:
-
Email, groupware, online reports, …
© 2002, AvaQuest Inc.
Example 2:
Simple KM People Finder
Ranked People Names
Name
Extractor
Query
Search or
Navigation
System
Relevant
Docs
© 2002, AvaQuest Inc.
Authority
List
Example 2:
KM People Finder
© 2002, AvaQuest Inc.
Example 3:
Personalized Movie “Matcher”

The Need:
–

Match movies to individuals based on preference
profile
The Information:
–
–
Written reviews of movies
Users’ lists of favorite movies.
Movie
Reviews
Sentiment
Analysis
© 2002, AvaQuest Inc.
Typed and
Tagged
Reviews
Sentiment Analysis of Movies:
Visualization (after Evans)
absurdity
insecurity
Action
Romance
conflict
1
crime
injustice
0
inferiority
death
deception
immorality
horror
destruction
fear
© 2002, AvaQuest Inc.
Commercial Tools








IBM Intelligent Miner for Text
Semio Map
InXight LinguistX / ThingFinder
LexiQuest
ClearForest
Teragram
SRA NetOwl Extractor
Autonomy
© 2002, AvaQuest Inc.
User Interfaces for Text
Mining


Need some way to present results of Text
Mining in an intuitive, easy to manage form.
Options:
–
–
–
Conventional text “lists” (1D)
Charts and graphs (2D)
Advanced visualization tools (3D+)



Network maps
Landscapes
3d “spaces”
© 2002, AvaQuest Inc.
UI Challenges
Simple lists, charts, and graphs not
obviously applicable or difficult to
work with due to high dimensionality
of text
Advanced visualization tools can
be intimidating for the general
community and are not readily
accepted
© 2002, AvaQuest Inc.
Charts and Graphs
http://www.cognos.com/
© 2002, AvaQuest Inc.
Visualization: Network Maps
http://www.thinkmap.com/
© 2002, AvaQuest Inc.
Visualization: Network Maps
http://www.lexiquest.com/
© 2002, AvaQuest Inc.
Visualization: Landscapes
http://www.aurigin.com/
© 2002, AvaQuest Inc.
Visualization: 3D Spaces
http://zing.ncsl.nist.gov/~cugini/uicd/cc-paper.html
© 2002, AvaQuest Inc.
The Future


Different tools and data, but common dimensions
Example:
–
–
“Find sales trends by product and correlate with occurrences of
company name in business news articles”
Dimensions: Time, Company names (or stock symbols), Product
names, Regions
© 2002, AvaQuest Inc.
Recent Events

February 2002
–

Meta Group posts report arguing for need to
integrate business intelligence applications with
knowledge management portals.
March 2002
–
SAS, leading provider of business intelligence
software solutions, partners with Inxight to introduce
true text mining product.
© 2002, AvaQuest Inc.